A trip energy estimation system for a vehicle includes a traffic speed module configured to determine an average traffic speed along a projected route, a path information module configured to output path information indicating route features along the projected route, a perceived speed module configured to output a perceived vehicle speed along the projected route based on the average traffic speed and the path information, and a dynamic driving module configured to calculate and output a predicted driver speed based on the perceived vehicle speed and a feedback input indicative of the predicted driver speed. The dynamic driving module is configured to execute a machine learning algorithm to calculate the predicted driver speed.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The trip energy estimation system of claim 1, wherein the machine learning algorithm corresponds to a dynamic function.
3. The trip energy estimation system of claim 1, wherein the machine learning algorithm corresponds to a nonlinear autoregressive network with exogenous inputs (NARX) network.
4. The trip energy estimation system of claim 1, wherein the machine learning algorithm corresponds to a layer recurrent neural network which is based on a history of vehicle speed.
5. The trip energy estimation system of claim 1, wherein the dynamic driving module is configured to calculate the predicted driver speed as a function of a neural network NNT in accordance with NNT(V(t−1), V(t−2), x(t), x(t−1), x(t−2)), wherein V is vehicle speed, t is a sample time, and x corresponds to one or more other variable inputs.
6. The trip energy estimation system of claim 1, wherein the dynamic driving module is configured to calculate the predicted driver speed further based on at least one of grade information and turn information along the projected route.
8. The trip energy estimation system of claim 1, further comprising a distance module configured to calculate a distance travelled along the projected route based on the predicted driver speed.
9. The trip energy estimation system of claim 8, wherein each of the path information module and the traffic speed module receives the calculated distance.
10. The trip energy estimation system of claim 1, wherein the traffic (Original) speed module is configured to determine the average traffic speed along the projected route as a function of distance and the perceived speed module is configured to determine the perceived vehicle speed along the projected route as a function of time.
11. A vehicle comprising the trip energy estimation system of claim 1.
13. The method of claim 12, wherein the machine learning algorithm corresponds to at least one of a neural network toolbox (NNT), a nonlinear autoregressive network with exogenous inputs (NARX) network, and a layer recurrent neural network which is based on a history of vehicle speed.
14. The method of claim 12, further comprising calculating the predicted driver speed as a function of a neural network NNT in accordance with NNT (V(t−1), V(t−2), x(t), x(t−1), x(t−2)), wherein V is vehicle speed, t is a sample time, and x corresponds to one or more other variable inputs.
15. The method of claim 12, further comprising calculating the predicted driver speed further based on at least one of grade information and turn information along the projected route.
16. The method of claim 12, further comprising determining the average traffic speed along a projected route as a function of distance and determining the perceived vehicle speed along the projected route as a function of time.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 22, 2022
November 26, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.